Intelligent Embedded Monitoring System of Hydraulic CNC Machine Tool

Abstract

This paper designs the hydraulic CNC machine tool monitoring system based on the intelligent embedded theory. The mass data generated during the operation of the equipment is collected via the network. The diagnosis expert system is used to interpret these state data to achieve pre-judgment of fault, improve the equipment reliability and reduce the operating cost. The high-frequency network-based servo data sampling technology is developed using FANUC open Focas dynamic link database. The storage and management methods based on big data are studied. The upper layer data management framework is built. Open-source Historian real-time database is used for data mining. Finally, the diagnosis model is established to interpret the abstract data, and establish a relationship with the machine failure mode. The model of servo lean energy consumption is obtained by studying the energy consumption under different modes of CNC machine tool to optimize the energy consumption.